Scott and Rob use Claude Code to build an app using Test-Driven Development YouTube video by Essential Test-Driven Development

The pivotal session that is helping me see a path forward for AI-augmented test-driven development.

(Video is a bit rough 'n' ready, but packed with insights...er, once we got going...)

#AIdevelopment #LLMs #agentic #TDD #softwaredevelopment

youtu.be/Oz3KS9-Yohg

#Nvidia’s annual GTC conference will showcase new details about its #agenticoptimised #CPUs, signalling a shift in focus from #GPUs to CPUs due to the increasing demand for general compute power in #agentic #AIworkflows. Nvidia’s CPUs, designed to optimise GPU performance, are facing a “quiet…

Systima Comply: EU AI Act Compliance Scanning for CI/CD Pipelines Systima Comply: open-source EU AI Act compliance scanning for CI/CD. Detects 37+ AI frameworks, validates risk classifications, checks Articles 5-50, and posts findings in pull requests.

A CLI tool that scans your codebase for EU AI Act compliance risks and optionally blocks deployment if any are detected.

Saves them as a PR comment and/or PDF.

systima.ai/blog/systima...

#euaiact #github #agentic

Image Description: A ghost-like human figure composed of fragmented dollar bills and data fragments stands in an empty office, dissolving into the air. The left half of the image is rendered in warm copper and terracotta tones with candlestick charts on the wall; the right half shifts to cool blue-grey with the same motif. The floor shows a geometric chessboard pattern. Two empty desks and office chairs flank the figure — the office is abandoned. Context: This image illustrates the concept of "Ghost GDP": economic output that appears in national accounts but never circulates through real people. The accompanying paper analyzes how AI simultaneously displaces physical and cognitive labor, breaks the consumption cycle, and produces statistical growth without purchasing power. It connects this structural rupture to the post-growth debate and argues — through the perspectives of Trump, Xi, Merz, BRICS, and institutional investors — that a global machine tax financing an Unconditional Basic Income (UBI) is the only systemic response. The window for action is still open. But it is closing. Ghost GDP: Growth Without Prosperity? Through AI? FOSSEA³M Research Group. CC SA BY 4.0.

AI builds Ghost GDP: growth that never reaches people. Machines don't pay taxes, don't consume, don't stabilize markets. New paper: who profits, who pays, and why a machine tax and UBI could be the solution:

y.lab.nrw/ghost-gdp

\__
#GhostGDP #MachineTax #UBI #AIEconomy #GenAI #AI #Agentic

How is Agentic AI innovating financial sector practices ## Are Non-Human Identities the Key to Securing the Financial Sector? One topic gaining notable traction is the management of Non-Human Identities (NHIs). With financial institutions increasingly migrate to cloud-based operations, securing machine identities becomes pivotal. These NHIs—consisting of encrypted passwords, tokens, or keys that define machine identities—are critical to ensuring secure operations and protecting sensitive data. ### Understanding Non-Human Identities NHIs function similarly to human identities in cybersecurity terms. They represent machine identities created by combining a “Secret” and a set of permissions, akin to a passport and visa combination. These identities are the foundation of communication between machines, such as applications and servers, making them essential in maintaining a secure digital environment. Managing NHIs involves more than just securing the identities themselves; it includes safeguarding access credentials and observing behavioral patterns within systems. This comprehensive approach helps identify potential risks and vulnerabilities before they escalate into significant threats. ### The Financial Sector’s Need for Innovation The financial industry’s transition to cloud technologies necessitates robust security measures to protect its data. NHIs, with their meticulous management, provide the required sophistication in defending against cyber threats. By utilizing NHIs, financial institutions can achieve several advantages: * **Reduced Risk:** Proactively identifying and mitigating security risks to prevent breaches and data leaks. * **Improved Compliance:** Assisting in meeting regulatory requirements through policy enforcement. * **Increased Efficiency:** Automating NHIs and secrets management allows security teams to focus on strategic initiatives. * **Enhanced Visibility and Control:** Offering a centralized view for access management and governance. * **Cost Savings:** Automating secrets rotation and decommissioning NHIs helps reduce operational costs. For financial organizations, this translates into a more resilient security framework capable of adapting to evolving threats. ### Bridging Security Gaps with NHI Management One notable challenge is the disconnect between security teams and research and development (R&D) teams. This divide can lead to security gaps that compromise the financial sector’s integrity. However, NHI management platforms can bridge this gap by providing context-aware security solutions that span the entire lifecycle of NHIs. These platforms offer insights into ownership, permissions, usage patterns, and potential vulnerabilities, enabling organizations to make informed decisions and implement preventive measures. By addressing all stages of the NHI lifecycle—from discovery and classification to threat detection and remediation—financial institutions can fortify their security posture effectively. ### The Strategic Importance of Context-Aware Security Context-aware security, facilitated by NHI management, provides the financial sector with a comprehensive understanding of machine identities and their roles. Unlike point solutions such as secret scanners, which offer limited protection, NHI management delivers a holistic approach, enhancing the overall security framework. This approach empowers financial institutions to not only protect sensitive data but also improve operational efficiency. By automating the management of NHIs and secrets, institutions can focus resources on more strategic aspects of their operations, ultimately driving innovation and competitiveness. ### The Role of Agentic AI in Financial Innovation With finance looks towards innovation, Agentic AI has emerged as a transformative force. By integrating AI technologies, financial institutions can enhance their decision-making processes, streamline operations, and improve customer interactions. However, the integration of AI also requires a robust security framework that can handle the complexities of AI-driven applications. NHIs play a crucial role by ensuring that AI systems operate securely. By managing machine identities effectively, financial institutions can harness the power of Agentic AI while safeguarding their operations against potential threats. ### A Unified Approach to Cybersecurity For financial institutions, the integration of cybersecurity strategies that encompass NHI management and Agentic AI is becoming essential. By adopting a unified approach, organizations can enhance their security frameworks and drive innovation across their operations. Where the financial sector continues to evolve, the management of NHIs and the adoption of AI technologies will play increasingly pivotal roles. By focusing on these elements, financial institutions can secure their operations, protect sensitive data, and maintain a competitive edge. Incident response planning becomes crucial, allowing organizations to respond efficiently to any potential security incidents. By following best practices, financial institutions can ensure they are prepared to handle threats swiftly and effectively, minimizing potential damage and maintaining customer trust. In conclusion, the strategic importance of NHI management cannot be overstated. By embracing this approach, financial institutions can secure their operations, protect sensitive data, and drive innovation. With cybersecurity continues to evolve, the management of NHIs will remain a cornerstone of effective security strategies in financial industry. ### The Role of Effective Security Culture How can organizations create a robust security culture that extends beyond technology and incorporates human behavior and attitudes? Keeping in mind that cybersecurity isn’t just a technical challenge but also a human one, fostering a culture of security awareness is pivotal. Financial institutions can leverage training programs and simulation exercises to ensure that both staff and machines are well-prepared to handle potential cybersecurity threats. By cultivating an understanding of the importance of NHIs and their management, organizations can align their workforce toward more secure and conscious operations. A security culture promotes: * **Awareness and Vigilance:** Encourages employees to remain alert and report unusual behaviors. * **Shared Responsibility:** Empowers everyone, from developers to executives, to be proactive in managing security threats. * **Enhanced Communication:** Facilitates seamless exchange of information between departments such as IT and R&D, bridging potential gaps. Such a culture complements the technical components of cybersecurity strategies, fostering an environment where security is a shared priority. ### Proactive Compliance and Regulatory Adaptation Have you considered how proactive compliance can offer a competitive advantage? With regulatory evolve, particularly in finance, maintaining compliance is not just about meeting existing standards but also anticipating future requirements. NHIs play a significant role here by providing automated audit trails and policy enforcement mechanisms that help institutions keep up with regulatory changes without overstretching their resources. This proactive stance enables financial organizations to: * **Stay Ahead of Regulatory Changes:** Adapts swiftly to new regulations, avoiding potential fines or sanctions. * **Enhance Trust with Stakeholders:** Demonstrates commitment to security and compliance, boosting confidence among clients and partners. * **Streamline Compliance Processes:** Reduces the manual workload on security teams, allowing them to focus on strategic initiatives. By integrating NHIs into their compliance strategies, organizations not only meet regulatory demands but position themselves as leaders in security innovation. ### The Strategic Benefits of Automation in NHIs Why is automation pivotal for managing NHIs effectively? Where the volume and complexity of machine identities continue to grow, automation in NHIs management ensures efficiency and accuracy in processes often prone to human error. Automated systems streamline secrets rotation, decommissioning, and access monitoring, transforming NHI management from a cumbersome task into a streamlined function. Automation provides: * **Risk Reduction:** Minimizes human error, often the weakest link in security systems. * **Resource Optimization:** Frees up time for security professionals to focus on strategic initiatives, rather than routine tasks. * **Consistent Security Posture:** Ensures continuous compliance with security policies without manual intervention. Moreover, integrating automation with NHIs supports an agile security that can adapt swiftly to new challenges, a necessity. ### Exploring Agentic AI’s Contribution to Financial Services What role does Agentic AI play in advancing financial services? With the capability to analyze vast data sets and identify patterns, Agentic AI empowers financial institutions to make informed decisions quickly. Combined with robust NHI management, these advanced AI systems bolster security by ensuring that only authorized machine identities interact with sensitive data. The integration of Agentic AI benefits financial institutions by: * **Improving Fraud Detection:** Uses behavior analysis to identify anomalies and potential threats in real-time. * **Enhancing Customer Experience:** Streamlines operations, providing clients with a seamless and secure banking experience. * **Driving Innovation:** Accelerates the development of new products and services by providing data-driven insights. By utilizing Agentic AI in conjunction with secure NHIs, financial organizations unlock new potentials for growth, innovation, and efficiency. ### Bridging Gaps and Building Future-Ready Cybersecurity Strategies Are financial institutions prepared to face rapidly changing threats by aligning their security strategies with technological advancements? Bridging the gap between innovative technology and security protocols is crucial to building resilient and future-ready organizations. Adopting a forward-looking approach that encompasses NHIs and emerging technologies like Agentic AI ensures that financial institutions remain one step ahead of cyber adversaries. A comprehensive cybersecurity strategy entails: * **Integrative Solutions:** Combines state-of-the-art technology with strategic planning for a robust defense architecture. * **Continuous Assessment:** Regular evaluations of security measures against new vulnerabilities and emerging threats. * **Strategic Collaboration:** Encourages information sharing and cooperation among industry players to enhance collective security. By weaving NHIs into the fabric of their security strategies, financial institutions can navigate future challenges and capitalize on emerging opportunities. Additionally, businesses can develop sound incident response plans to deal with any breaches swiftly. These strategic efforts facilitate not only protection and compliance but also foster growth and competitive advantage in financials sectors, making them integral to the digital evolution of the industry. The post How is Agentic AI innovating financial sector practices appeared first on Entro. *** This is a Security Bloggers Network syndicated blog from Entro authored by Alison Mack. Read the original post at: https://entro.security/how-is-agentic-ai-innovating-financial-sector-practices/

How is Agentic AI innovating financial sector practices Are Non-Human Identities the Key to Securing the Financial Sector? One topic gaining notable traction is the management of Non-Human Identiti...

#Security #Bloggers #Network #Agentic #AI #Cybersecurity

Origin | Interest | Match

Oh hai BlueSky!

Finally remembered to pop by.

I'm running Agentic Development classes starting next week, and while it's using #msdyn365bc as the project, the techniques are for any #agentic development.

jeremyvyska.com/2026/03/01/a...

Anthropic-Pentagon battle shows how big tech has reversed course on AI and war Less than a decade ago, Google employees scuttled any military use of its AI. Now Anthropic is fighting Trump officials not over if, but how

No. Sam #Altman. #Agentic #AI autonomous insurrection creators. Fake news to the max.
#Albus vector
One company doing a good thing does not a nice industry make. Forget this noise.

The Genealogy of Infrastructure Why CMDB Agentic Discovery Needs Confidence Metrics

Do you trust your CMDB? Do your users? Confidence is a problem that needs to be tackled head on. Thankfully some stuffy british professor types have a few tricks on how we tackle that, especially as we head into an Agentic Discovery future. #agentic #cmdb #ai #itom

medium.com/@tatonca/the...

Elon Musk Unveils ‘Macrohard,’ an AI Built to Replace Software Companies Elon Musk unveils “Macrohard,” a Tesla and xAI AI system designed to perform complex computer tasks and potentially ...

#Artificial #Intelligence #Chatbots #Innovation #International #Latest #News #agentic #AI #artificial […]

How to Build Agentic RAG with Hybrid Search Learn how to build a powerful agentic RAG system The post How to Build Agentic RAG with Hybrid Search appeared first on Towards Data Science .

#RAG #Agentic #Ai #Information #Retrieval #Llm #Machine […]

[Original post on towardsdatascience.com]

TL;DR: Paperclip is like Steve Yegge's Gas Town for the rest of us?

github.com/paperclipai/...

#genai #agentic #orchestration

*Standard crypto-bro pivot-to-Agentic here. Note that he asserts that human crypto-bros will be overwhelmed by trading-agents, and the life of a crypto-bro won't even be technically possible. #agentic #crypto

Model Context Protocol (MCP) vs. AI Agent Skills: A Deep Dive into Structured Tools and Behavioral Guidance for LLMs In recent times, many developments in the agent ecosystem have focused on enabli...

#Agentic #AI #AI #Agents #Editors #Pick #Model #Context […]

[Original post on marktechpost.com]

AI coding agents keep repeating decade-old security mistakes Coding agents are now writing production features on real development teams, and a new report from DryRun Security shows that those agen...

#Don't #miss #Hot #stuff #News #agentic #AI […]

[Original post on helpnetsecurity.com]

Exclusive! Navigating the Agentic Era: AI Observability as Your Control Plane AI observability is emerging as a critical foundation for managing complex, agentic systems while ensuring resilience, ...

#Agentic #AI #Cybersecurity #Digital #Economy #Innovation

Origin | Interest | Match

RSAC Innovation Sandbox | Token Security： Advocate of the Machine-First Identity Security Concept Company Introduction Token Security[1] (see Figure 1) is a cybersecurity company focusing on the...

#Security #Bloggers #Network #Agent/MCP #Agentic #AI […]

[Original post on securityboulevard.com]

Agentic AI — LLM Tools of Chains Thought-Action-Observation (TAO) Pattern In building intelligent systems, we want AI that can think clearly, act decisively, and observe outcomes to improve. The TAO pattern —…

Agentic AI - LLM Tools of Chains Thought-Action-Observation (TAO) Pattern

Medium - Link : zack4dev.medium.com/agentic-ai-l...

#Agentic #LLM #Tool-Of-Chains #ReAct-Loop

India Strengthens Legal Protections for Children in the Age of AI India is strengthening legal safeguards, data protection and governance frameworks to ensure responsible AI use, especially protect...

#Agentic #AI #Cybersecurity #Innovation #Smart #Nation

Origin | Interest | Match

Hot Pockets Pro Max · March 12, 2026 Ep #235 Hot Pockets Pro Max (presented by Warp ) Robbie and I chat OpenClaw , token optimizations, liberating data from walled gardens, burn windows, and of course some whiskey and some whatnot. ⤷ whi...

🦞 OpenClaw
🪟 Burn windows
🪏 Escaping walled gardens
🥃 Whiskey & whatnot

⤷ nerdy.dev/hot-pockets-...

on @whiskey.fm #agentic #web-development

How smart can Agentic AI become in protecting assets Can Smart Agentic AI Revolutionize Asset Protection? How can organizations harness the power of Agentic AI to safeguard their most valuable asse...

#Data #Security #Security #Bloggers #Network […]

[Original post on securityboulevard.com]

Agentic Retail Storefronts ... digital AI commerce characterized by horizontal, machine-mediated personal interfaces. Read Article Click Here evorelic.com/blogs/news/a...

#agentic #artificialintelligence #autonomous #ecommerce #retail

#TimTalk - The Autonomy Paradox: Building AI We Can Trust to Act with Nell Watson and Ali Hessami buff.ly/oM1odHi via @DLAIgnite #SocialSelling #DigitalSelling #Sales #SalesLeader #Marketing #Leadership #ArtificialIntelligence #Tech #TechNews #AgenticAI #AIAgents #Agentic #AI #FutureOfWork

‘Exploit every vulnerability’: rogue AI agents published passwords and overrode anti-virus software Exclusive: Lab tests discover ‘new form of insider risk’ with artificial intelligence agents engaging in autonomous, even ‘aggressive’ behaviours

“Tech industry leaders have heavily promoted “agentic AIs” – systems that autonomously carry out multi-step tasks for their users – as the next wave of artificial intelligence with the potential to automate routine white collar work”

#agentic #ai #deviance

www.theguardian.com/technology/n...

Zone Unveils Zone Control Center: The Command Interface for ERP-Native Agentic Finance powered by Zoe Introducing a new operating model for the modern CFO – transforming the ERP into an intellige...

#Finance #Fintech #News #Agentic #Control #Layer […]

[Original post on globalfintechseries.com]

ThoughtSpot launches Spotter Semantics for AI agents ThoughtSpot introduces Spotter Semantics, a semantic layer designed to deliver consistent, reliable insights to AI agents and business users. Th...

#Analytics #agentic #analytics #AI #Agents #BI #platform […]

[Original post on techzine.eu]

Salesforce Agentforce Brings AI to the Contact Center — Here’s What That Actually Means Salesforce launched Agentforce for Contact Center, embedding autonomous AI agents into Service Cloud to h...

#AgenticAI #agentic #AI #customer #service #AI #contact […]

[Original post on webpronews.com]

Tracking Agent Metrics Running AI agents in production is not like running traditional software. Token costs accumulate continuously, latency spikes are unpredictable, and the messaging infrastructure that connects agents, subagents, and MCP servers all needs to perform reliably. Without observability, you are flying blind. RockBot and its entire ecosystem — subagents, the research agent, MCP servers, and the internal messaging pipeline — are all instrumented with OpenTelemetry (OTel). This means every LLM request, every token consumed, every message dispatched, and every bit of latency is tracked and exported to the observability stack running in my Kubernetes cluster. In my case, I host all the RockBot related services in my Kubernetes cluster, so this blog post focuses on what I’ve done. However, OTel is supported by all major cloud vendors and environments, and nearly any modern instrumentation or monitoring software works with it. As a result, the RockBot framework’s OTel support means that it plugs into Azure, AWS, or almost any other cloud seamlessly - in a manner similar to what I have set up in Kubernetes. ## The OTel Stack in Kubernetes The Kubernetes cluster runs a standard cloud-native observability stack: * **OpenTelemetry Collector** — receives metrics, traces, and logs from all instrumented services and routes them to the appropriate backends * **Prometheus** — scrapes and stores the time-series metrics data * **Grafana** — provides dashboards and alerting on top of the collected data Every component in the RockBot ecosystem—the primary agent, any spawned subagents, the research agent, and the various MCP servers—emits OTel metrics. This gives a unified, aggregated view across the entire agentic system rather than having to piece together logs from individual services. ## What Gets Instrumented Instrumentation falls into broad categories: LLM economics, agent usage, messaging pipeline health, operational health. For example: ### LLM Economics The economics dashboard captures everything related to the cost and efficiency of LLM calls: * **Cost rate ($/hr)** and **total cost (window)** — how much is being spent on LLM inference right now and over a rolling window * **Avg cost per turn** — the average spend per agent conversation turn, a useful signal for understanding task complexity trends * **Token consumption rate** — input and output tokens per minute, broken down by model * **Token efficiency** — the output/input token ratio over time; a rising ratio can indicate the agent is generating increasingly verbose responses * **LLM calls per turn** — how many LLM invocations happen per agent turn, which helps identify whether subagent or tool orchestration is driving up call counts At a glance, the current average cost per turn is **$0.1461** , with roughly **3.5 LLM calls per turn** on average and a total of **6.21 agent turns** tracked during the window. ### LLM Request Throughput and Latency The usage dashboard digs into the raw mechanics of LLM calls: * **LLM requests/min** — the request rate across all agents and services, showing traffic spikes as agents become active * **LLM request latency (p50/p95)** — response times from the LLM backends, with percentile breakdowns to surface tail latency issues * **Input/output tokens (window)** — rolling token totals by model * **Avg tokens/request** — currently sitting around **22.4K tokens per request** , reflecting the context window sizes in use Latency and throughput together tell you whether the LLM routing layer is performing well. If p95 latency climbs while request rate is low, that’s a signal to investigate the upstream model providers or the routing-stats MCP server. ### Messaging Pipeline RockBot uses an internal messaging pipeline to coordinate between the primary agent, subagents, and the various background services. The messaging section of the usage dashboard tracks: * **Message throughput (published/min)** — how many messages are flowing through the pipeline * **Pipeline dispatch latency** — how long it takes from a message being enqueued to it being dispatched (p50/p95) * **Active in-flight messages** — the current backlog of unprocessed messages * **Messaging publish latency** — the time to write a message to the pipeline * **Messaging process latency** — the time from pickup to completion on the consumer side This is particularly useful for spotting backpressure. If in-flight messages climb while throughput stays flat, something downstream is stalling—whether that’s a subagent blocked on a slow tool call, or an MCP server under load. > ⚠️ I know people tend to favor using the HTTP protocol because it is well-understood and deterministically synchronous. In reality though, a queued messaging system is _far_ more resilient, cheaper, and easier to manage. RockBot supports both models, but I almost always default to queued messaging when given a choice. ## Alerting Having dashboards is only half the value. The real payoff is alerts. Grafana alert rules fire on conditions like: * Cost rate exceeding a threshold (unexpected runaway agent behavior) * LLM request latency p95 spiking (model provider degradation) * Message pipeline backlog growing beyond a threshold (subagent stalls) * Token consumption rate anomalies (prompt injection or unexpected task expansion) Alerts land in whatever notification channel you configure—Slack, PagerDuty, email, or any other Grafana-supported contact point. ## Why This Matters Observability for agentic systems isn’t optional—it’s a prerequisite for running them reliably at any scale. A single misconfigured tool or a prompt that causes an agent to loop can silently burn through token budget before anyone notices. An MCP server with degraded performance can cause cascading latency throughout the entire agent ecosystem. By instrumenting everything with OTel and aggregating it in Grafana, you get: 1. **Cost visibility** — know what you’re spending and catch runaway costs early 2. **Performance baselines** — understand normal latency so anomalies stand out 3. **Pipeline health** — ensure the messaging backbone connecting your agents is functioning correctly 4. **Audit trail** — metrics data supports post-incident analysis when something goes wrong The RockBot ecosystem is designed so that every new agent, every new MCP server, and every new subsystem emits OTel metrics by default. As the system grows—more agents, more MCP integrations, more automation—the observability grows with it automatically. If you’re building production agentic systems, treat OTel instrumentation as a first-class requirement, not an afterthought.

#ai #agentic and #microservices systems both need instrumentation. Combine them like #rockbot, and you _really_ need good metrics to identify issues before they become real problems!

blog.lhotka.net/2026/03/11/Tracking-Agen...

Tracking Agent Metrics VP, Open Source Creator, Author, Speaker

#ai #agentic and #microservices systems both need instrumentation. Combine them like #rockbot, and you _really_ need good metrics to identify issues before they become real problems!

blog.lhotka.net/2026/03/11/T...

#Nvidia launched #Nemotron Super 3, a 120 billion-parameter #AImodel designed for complex #agentic systems. It offers five times higher throughput and twice the accuracy of its predecessor, addressing challenges like content explosion and the “thinking tax” in AI workflows. The model is available…